Author: JOSE ORTIZ BEJAR

A Family of Classifiers based on Feature Space Transformations and Model Selection

José Ortiz Bejar (2020)

Improving the performance of classifiers is the realm of feature mapping, prototype selection, and kernel function transformations; these techniques aim for reducing the complexity, and also, improving the accuracy of models. In particular, the research’s objective is to combine them to transform data’s shape into another more convenient distribution; such that some simple algorithms, such as Naïve Bayes and k-Nearest Neighbors, can produce competitive classifiers. In this work, we introduce a family of classifiers based on feature mapping and kernel functions, orchestrated by simple a model selection scheme that achieves excel in performance. We provide an extensive experimental comparison of our methods with sixteen popular classifiers over different datasets supporting our claims. In addition to their competitive performance, our statistical tests also found that our methods are statistically different among them, and thus, an effective family of classifiers.

Tesis

Other

Doctoral Degree Work

Ciencia de datos Tecnologías de la información y comunicación Datos estadísticos INGENIERÍA Y TECNOLOGÍA CIENCIAS TECNOLÓGICAS OTRAS ESPECIALIDADES TECNOLÓGICAS OTRAS OTRAS

Image annotation as Text-Image matching: Challenge design and results

Luis Luis Pellegrin OCTAVIO LOYOLA GONZALEZ JOSE ORTIZ BEJAR MIGUEL ANGEL MEDINA PEREZ ANDRES EDUARDO GUTIERREZ RODRIGUEZ Eric Sadit Téllez Avila MARIO GRAFF GUERRERO SABINO MIRANDA JIMENEZ Daniela Moctezuma MAURICIO ALFONSO GARCIA LIMON ALICIA MORALES REYES CARLOS ALBERTO REYES GARCIA Eduardo Morales Manzanares Hugo Jair Escalante (2019)

This paper describes the design of the 2017 RedICA: Text-Image Matching (RICATIM) challenge, including the dataset generation, a complete analysis of results, and the descriptions of the top-ranked developed methods. The academic challenge explores the feasibility of a novel binary image classification scenario, where each instance corresponds to the concatenation of learned representations of an image and a word. Instances are labeled as positive if the word is relevant for describing the visual content of the image, and negative otherwise. This novel approach of the image classification problem poses an alternative scenario where any text-image pair can be represented in such space, so any word could be considered for describing an image. The proposed methods are diverse and competitive, showing considerable improvements over the proposed baselines.

Article

Text-image matching Image annotation Multimodal information processing INGENIERÍA Y TECNOLOGÍA CIENCIAS TECNOLÓGICAS OTRAS ESPECIALIDADES TECNOLÓGICAS OTRAS OTRAS